Disable retries for stats payload sends by VianneyRuhlmann · Pull Request #2249 · DataDog/libdatadog

VianneyRuhlmann · 2026-07-17T15:56:57Z

What does this PR do?

Makes StatsExporter send stats payloads with no retries (single attempt) instead of the default 5-retry exponential backoff.

Motivation

The Client-Side Stats spec (v1.2.0, Flush Requirements) mandates "No Retry Logic: Stats are fire-and-forget; failed payloads are not retried" and that transport errors must not block stats computation.

Spec: datadoghq.atlassian.net/wiki/spaces/APM/pages/5758458333/v1.2.0#Flush-Requirements

Changes

send_payload now passes RetryStrategy::new(0, 0, RetryBackoffType::Constant, None) instead of RetryStrategy::default().
Updated test_send_stats_fail to expect a single request attempt instead of 6 (initial + 5 retries).

How to test the change?

cargo check -p libdd-trace-stats and cargo nextest run -p libdd-trace-stats (couldn't run in sandbox: a git dependency is blocked by the network allowlist).

PR by Bits - View session in Datadog

Comment @DataDog to request changes

datadog-prod-us1-6 · 2026-07-17T15:56:58Z

View session in Datadog

Bits Code status: ✅ Done

CI Auto-fix: Disabled | Enable

Comment @DataDog to request changes

datadog-datadog-prod-us1-2 · 2026-07-17T15:57:02Z

I can only run on private repositories.

github-actions · 2026-07-17T15:58:59Z

📚 Documentation Check Results

⚠️ 872 documentation warning(s) found

📦 `libdd-trace-stats` - 872 warning(s)

Updated: 2026-07-17 16:08:04 UTC | Commit: 10c64e5 | missing-docs job results

github-actions · 2026-07-17T16:00:48Z

🔒 Cargo Deny Results

⚠️ 2 issue(s) found, showing only errors (advisories, bans, sources)

📦 `libdd-trace-stats` - 2 error(s)

Show output

error[vulnerability]: Invalid pointer dereference in `fmt::Pointer` impl for `Atomic` and `Shared` when the underlying pointer is invalid
   ┌─ /home/runner/work/libdatadog/libdatadog/Cargo.lock:66:1
   │
66 │ crossbeam-epoch 0.9.18 registry+https://github.com/rust-lang/crates.io-index
   │ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ security vulnerability detected
   │
   ├ ID: RUSTSEC-2026-0204
   ├ Advisory: https://rustsec.org/advisories/RUSTSEC-2026-0204
   ├ Affected versions of `fmt::Display` dereference the underlying pointer. This causes a invalid pointer dereference e.g., when a pointer created with `Atomic::null` or `Shared::null`. `fmt::Debug` impls and pre-0.9 `fmt::Display` impls, which do not dereference pointers, are not affected by this issue.
   ├ Announcement: https://github.com/crossbeam-rs/crossbeam/pull/1276
   ├ Solution: Upgrade to >=0.9.20 (try `cargo update -p crossbeam-epoch`)
   ├ crossbeam-epoch v0.9.18
     └── crossbeam-deque v0.8.5
         └── rayon-core v1.12.1
             └── rayon v1.10.0
                 └── criterion v0.5.1
                     ├── libdd-common v5.1.0
                     │   ├── libdd-capabilities-impl v3.0.0
                     │   │   ├── libdd-shared-runtime v2.0.0
                     │   │   │   ├── libdd-telemetry v6.0.0
                     │   │   │   │   └── libdd-trace-stats v6.0.0
                     │   │   │   └── libdd-trace-stats v6.0.0 (*)
                     │   │   ├── libdd-trace-stats v6.0.0 (*)
                     │   │   └── libdd-trace-utils v9.0.0
                     │   │       ├── libdd-trace-obfuscation v5.0.0
                     │   │       │   └── libdd-trace-stats v6.0.0 (*)
                     │   │       ├── libdd-trace-stats v6.0.0 (*)
                     │   │       └── (dev) libdd-trace-utils v9.0.0 (*)
                     │   ├── libdd-dogstatsd-client v4.0.0
                     │   │   └── libdd-trace-stats v6.0.0 (*)
                     │   ├── libdd-shared-runtime v2.0.0 (*)
                     │   ├── libdd-telemetry v6.0.0 (*)
                     │   ├── libdd-trace-obfuscation v5.0.0 (*)
                     │   ├── libdd-trace-stats v6.0.0 (*)
                     │   └── libdd-trace-utils v9.0.0 (*)
                     ├── (dev) libdd-ddsketch v1.1.0
                     │   ├── libdd-telemetry v6.0.0 (*)
                     │   └── libdd-trace-stats v6.0.0 (*)
                     ├── (dev) libdd-trace-normalization v3.0.0
                     │   └── libdd-trace-utils v9.0.0 (*)
                     ├── (dev) libdd-trace-obfuscation v5.0.0 (*)
                     ├── (dev) libdd-trace-stats v6.0.0 (*)
                     └── (dev) libdd-trace-utils v9.0.0 (*)

error[unsound]: Rand is unsound with a custom logger using `rand::rng()`
    ┌─ /home/runner/work/libdatadog/libdatadog/Cargo.lock:198:1
    │
198 │ rand 0.8.5 registry+https://github.com/rust-lang/crates.io-index
    │ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ unsound advisory detected
    │
    ├ ID: RUSTSEC-2026-0097
    ├ Advisory: https://rustsec.org/advisories/RUSTSEC-2026-0097
    ├ It has been reported (by [@lopopolo](https://github.com/lopopolo)) that the `rand` library is [unsound](https://rust-lang.github.io/unsafe-code-guidelines/glossary.html#soundness-of-code--of-a-library) (i.e. that safe code using the public API can cause Undefined Behaviour) when all the following conditions are met:
      
      - The `log` and `thread_rng` features are enabled
      - A [custom logger](https://docs.rs/log/latest/log/#implementing-a-logger) is defined
      - The custom logger accesses `rand::rng()` (previously `rand::thread_rng()`) and calls any `TryRng` (previously `RngCore`) methods on `ThreadRng`
      - The `ThreadRng` (attempts to) reseed while called from the custom logger (this happens every 64 kB of generated data)
      - Trace-level logging is enabled or warn-level logging is enabled and the random source (the `getrandom` crate) is unable to provide a new seed
      
      `TryRng` (previously `RngCore`) methods for `ThreadRng` use `unsafe` code to cast `*mut BlockRng<ReseedingCore>` to `&mut BlockRng<ReseedingCore>`. When all the above conditions are met this results in an aliased mutable reference, violating the Stacked Borrows rules. Miri is able to detect this violation in sample code. Since construction of [aliased mutable references is Undefined Behaviour](https://doc.rust-lang.org/stable/nomicon/references.html), the behaviour of optimized builds is hard to predict.
    ├ Announcement: https://github.com/rust-random/rand/pull/1763
    ├ Solution: Upgrade to >=0.10.1 OR <0.10.0, >=0.9.3 OR <0.9.0, >=0.8.6 (try `cargo update -p rand`)
    ├ rand v0.8.5
      ├── libdd-common v5.1.0
      │   ├── libdd-capabilities-impl v3.0.0
      │   │   ├── libdd-shared-runtime v2.0.0
      │   │   │   ├── libdd-telemetry v6.0.0
      │   │   │   │   └── libdd-trace-stats v6.0.0
      │   │   │   └── libdd-trace-stats v6.0.0 (*)
      │   │   ├── libdd-trace-stats v6.0.0 (*)
      │   │   └── libdd-trace-utils v9.0.0
      │   │       ├── libdd-trace-obfuscation v5.0.0
      │   │       │   └── libdd-trace-stats v6.0.0 (*)
      │   │       ├── libdd-trace-stats v6.0.0 (*)
      │   │       └── (dev) libdd-trace-utils v9.0.0 (*)
      │   ├── libdd-dogstatsd-client v4.0.0
      │   │   └── libdd-trace-stats v6.0.0 (*)
      │   ├── libdd-shared-runtime v2.0.0 (*)
      │   ├── libdd-telemetry v6.0.0 (*)
      │   ├── libdd-trace-obfuscation v5.0.0 (*)
      │   ├── libdd-trace-stats v6.0.0 (*)
      │   └── libdd-trace-utils v9.0.0 (*)
      ├── (dev) libdd-ddsketch v1.1.0
      │   ├── libdd-telemetry v6.0.0 (*)
      │   └── libdd-trace-stats v6.0.0 (*)
      ├── (dev) libdd-trace-normalization v3.0.0
      │   └── libdd-trace-utils v9.0.0 (*)
      ├── (dev) libdd-trace-stats v6.0.0 (*)
      ├── libdd-trace-utils v9.0.0 (*)
      └── proptest v1.5.0
          └── (dev) libdd-tinybytes v1.1.1
              ├── (dev) libdd-tinybytes v1.1.1 (*)
              └── libdd-trace-utils v9.0.0 (*)

advisories FAILED, bans ok, sources ok

Updated: 2026-07-17 16:08:04 UTC | Commit: 10c64e5 | dependency-check job results

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 8e120341e7

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

datadog-prod-us1-6 · 2026-07-17T16:04:35Z

Tests

⚠️ Warnings

🚦 3 Pipeline jobs failed

semver-check | validate

Required checks pass | allchecks

pr-name | pr_name_lint

ℹ️ Info

No other issues found (see more)

🧪 All tests passed
❄️ No new flaky tests detected

🎯 Code Coverage (details)
• Patch Coverage: 100.00%
• Overall Coverage: 74.69% (-0.04%)

Useful? React with 👍 / 👎

_{This comment will be updated automatically if new data arrives.

🔗 Commit SHA: aa352ce | Docs | Datadog PR Page | Give us feedback!}

pr-commenter · 2026-07-17T16:10:12Z

Benchmarks

Comparison

Benchmark execution time: 2026-07-17 16:19:21

Comparing candidate commit aa352ce in PR branch dd/no-retry-stats-payload with baseline commit 0c6e2a5 in branch main.

Found 0 performance improvements and 2 performance regressions! Performance is the same for 22 metrics, 0 unstable metrics.

Explanation

This is an A/B test comparing a candidate commit's performance against that of a baseline commit. Performance changes are noted in the tables below as:

🟩 = significantly better candidate vs. baseline
🟥 = significantly worse candidate vs. baseline

We compute a confidence interval (CI) over the relative difference of means between metrics from the candidate and baseline commits, considering the baseline as the reference.

If the CI is entirely outside the configured SIGNIFICANT_IMPACT_THRESHOLD (or the deprecated UNCONFIDENCE_THRESHOLD), the change is considered significant.

Feel free to reach out to #apm-benchmarking-platform on Slack if you have any questions.

More details about the CI and significant changes

You can imagine this CI as a range of values that is likely to contain the true difference of means between the candidate and baseline commits.

CIs of the difference of means are often centered around 0%, because often changes are not that big:

---------------------------------(------|---^--------)-------------------------------->
                              -0.6%    0%  0.3%     +1.2%
                                 |          |        |
         lower bound of the CI --'          |        |
sample mean (center of the CI) -------------'        |
         upper bound of the CI ----------------------'

As described above, a change is considered significant if the CI is entirely outside the configured SIGNIFICANT_IMPACT_THRESHOLD (or the deprecated UNCONFIDENCE_THRESHOLD).

For instance, for an execution time metric, this confidence interval indicates a significantly worse performance:

----------------------------------------|---------|---(---------^---------)---------->
                                       0%        1%  1.3%      2.2%      3.1%
                                                  |   |         |         |
       significant impact threshold --------------'   |         |         |
                      lower bound of CI --------------'         |         |
       sample mean (center of the CI) --------------------------'         |
                      upper bound of CI ----------------------------------'

scenario:trace_buffer/4_senders/no_delay

🟥 execution_time [+158.852µs; +186.606µs] or [+6.806%; +7.995%]
🟥 throughput [-116763.726op/s; -98954.163op/s] or [-7.560%; -6.407%]

Benchmark execution time: 2026-07-17 16:14:20

Comparing candidate commit aa352ce in PR branch dd/no-retry-stats-payload with baseline commit 0c6e2a5 in branch main.

Found 0 performance improvements and 0 performance regressions! Performance is the same for 3 metrics, 0 unstable metrics.

Explanation

This is an A/B test comparing a candidate commit's performance against that of a baseline commit. Performance changes are noted in the tables below as:

🟩 = significantly better candidate vs. baseline
🟥 = significantly worse candidate vs. baseline

We compute a confidence interval (CI) over the relative difference of means between metrics from the candidate and baseline commits, considering the baseline as the reference.

If the CI is entirely outside the configured SIGNIFICANT_IMPACT_THRESHOLD (or the deprecated UNCONFIDENCE_THRESHOLD), the change is considered significant.

Feel free to reach out to #apm-benchmarking-platform on Slack if you have any questions.

More details about the CI and significant changes

You can imagine this CI as a range of values that is likely to contain the true difference of means between the candidate and baseline commits.

CIs of the difference of means are often centered around 0%, because often changes are not that big:

---------------------------------(------|---^--------)-------------------------------->
                              -0.6%    0%  0.3%     +1.2%
                                 |          |        |
         lower bound of the CI --'          |        |
sample mean (center of the CI) -------------'        |
         upper bound of the CI ----------------------'

As described above, a change is considered significant if the CI is entirely outside the configured SIGNIFICANT_IMPACT_THRESHOLD (or the deprecated UNCONFIDENCE_THRESHOLD).

For instance, for an execution time metric, this confidence interval indicates a significantly worse performance:

----------------------------------------|---------|---(---------^---------)---------->
                                       0%        1%  1.3%      2.2%      3.1%
                                                  |   |         |         |
       significant impact threshold --------------'   |         |         |
                      lower bound of CI --------------'         |         |
       sample mean (center of the CI) --------------------------'         |
                      upper bound of CI ----------------------------------'

Candidate

Candidate benchmark details

Group 1

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz	`aa352ce`	1784304193	dd/no-retry-stats-payload

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
trace_buffer/1_senders/10us_delay	execution_time	56.384ms	56.739ms ± 0.292ms	56.639ms ± 0.140ms	56.851ms	57.403ms	57.541ms	57.588ms	1.67%	1.242	0.764	0.51%	0.021ms	1	200
trace_buffer/1_senders/10us_delay	throughput	15628.312op/s	15862.420op/s ± 81.202op/s	15890.079op/s ± 39.395op/s	15920.288op/s	15951.873op/s	15956.165op/s	15961.876op/s	0.45%	-1.224	0.712	0.51%	5.742op/s	1	200
trace_buffer/1_senders/1us_delay	execution_time	50.027ms	50.087ms ± 0.028ms	50.083ms ± 0.010ms	50.093ms	50.142ms	50.188ms	50.210ms	0.25%	1.362	3.002	0.06%	0.002ms	1	200
trace_buffer/1_senders/1us_delay	throughput	17924.559op/s	17968.791op/s ± 10.183op/s	17970.223op/s ± 3.631op/s	17973.954op/s	17982.754op/s	17988.239op/s	17990.352op/s	0.11%	-1.357	2.985	0.06%	0.720op/s	1	200
trace_buffer/1_senders/no_delay	execution_time	334.253µs	340.382µs ± 3.502µs	339.759µs ± 1.701µs	341.837µs	345.857µs	355.910µs	357.516µs	5.23%	2.099	6.996	1.03%	0.248µs	1	200
trace_buffer/1_senders/no_delay	throughput	2517370.033op/s	2644359.920op/s ± 26649.693op/s	2648936.055op/s ± 13262.017op/s	2660727.660op/s	2674637.708op/s	2683990.300op/s	2692571.196op/s	1.65%	-1.961	6.275	1.01%	1884.418op/s	1	200
trace_buffer/2_senders/10us_delay	execution_time	56.688ms	57.121ms ± 0.176ms	57.106ms ± 0.119ms	57.234ms	57.421ms	57.533ms	57.555ms	0.79%	0.189	-0.464	0.31%	0.012ms	1	200
trace_buffer/2_senders/10us_delay	throughput	31274.185op/s	31512.453op/s ± 97.098op/s	31520.097op/s ± 66.088op/s	31583.186op/s	31666.514op/s	31714.170op/s	31752.547op/s	0.74%	-0.175	-0.468	0.31%	6.866op/s	1	200
trace_buffer/2_senders/1us_delay	execution_time	50.058ms	50.114ms ± 0.032ms	50.110ms ± 0.016ms	50.126ms	50.180ms	50.211ms	50.222ms	0.23%	1.169	1.402	0.06%	0.002ms	1	200
trace_buffer/2_senders/1us_delay	throughput	35840.523op/s	35917.910op/s ± 22.576op/s	35921.188op/s ± 11.720op/s	35932.887op/s	35945.886op/s	35950.623op/s	35958.086op/s	0.10%	-1.165	1.392	0.06%	1.596op/s	1	200
trace_buffer/2_senders/no_delay	execution_time	858.540µs	904.819µs ± 19.354µs	904.915µs ± 11.736µs	915.995µs	929.893µs	962.479µs	1035.121µs	14.39%	1.656	9.917	2.13%	1.369µs	1	200
trace_buffer/2_senders/no_delay	throughput	1738927.887op/s	1990226.703op/s ± 41346.647op/s	1989136.194op/s ± 25505.913op/s	2018208.338op/s	2055732.955op/s	2078027.014op/s	2096582.028op/s	5.40%	-1.144	6.501	2.07%	2923.649op/s	1	200
trace_buffer/4_senders/10us_delay	execution_time	57.194ms	57.487ms ± 0.136ms	57.473ms ± 0.095ms	57.572ms	57.737ms	57.826ms	57.946ms	0.82%	0.523	0.258	0.24%	0.010ms	1	200
trace_buffer/4_senders/10us_delay	throughput	62127.207op/s	62623.266op/s ± 148.168op/s	62637.628op/s ± 104.174op/s	62740.087op/s	62820.119op/s	62918.142op/s	62943.608op/s	0.49%	-0.509	0.234	0.24%	10.477op/s	1	200
trace_buffer/4_senders/1us_delay	execution_time	50.115ms	50.175ms ± 0.037ms	50.166ms ± 0.016ms	50.186ms	50.263ms	50.278ms	50.289ms	0.25%	1.299	1.353	0.07%	0.003ms	1	200
trace_buffer/4_senders/1us_delay	throughput	71586.041op/s	71749.405op/s ± 52.542op/s	71761.723op/s ± 23.086op/s	71783.709op/s	71810.536op/s	71828.755op/s	71834.333op/s	0.10%	-1.296	1.344	0.07%	3.715op/s	1	200
trace_buffer/4_senders/no_delay	execution_time	2.365ms	2.507ms ± 0.049ms	2.514ms ± 0.032ms	2.543ms	2.580ms	2.591ms	2.642ms	5.08%	-0.514	-0.035	1.96%	0.003ms	1	200
trace_buffer/4_senders/no_delay	throughput	1362792.509op/s	1436705.841op/s ± 28588.592op/s	1431956.231op/s ± 18449.855op/s	1453878.580op/s	1492882.640op/s	1509596.856op/s	1522376.948op/s	6.31%	0.614	0.067	1.98%	2021.519op/s	1	200
trace_buffer/8_senders/10us_delay	execution_time	57.658ms	57.959ms ± 0.207ms	57.887ms ± 0.109ms	58.102ms	58.369ms	58.495ms	58.556ms	1.16%	0.894	-0.055	0.36%	0.015ms	1	200
trace_buffer/8_senders/10us_delay	throughput	122958.916op/s	124227.536op/s ± 442.095op/s	124379.321op/s ± 233.280op/s	124554.283op/s	124785.327op/s	124831.658op/s	124873.691op/s	0.40%	-0.882	-0.083	0.35%	31.261op/s	1	200
trace_buffer/8_senders/1us_delay	execution_time	50.205ms	50.297ms ± 0.061ms	50.274ms ± 0.028ms	50.324ms	50.427ms	50.505ms	50.534ms	0.52%	1.406	2.002	0.12%	0.004ms	1	200
trace_buffer/8_senders/1us_delay	throughput	142478.182op/s	143149.031op/s ± 174.477op/s	143213.774op/s ± 80.740op/s	143267.960op/s	143337.994op/s	143384.954op/s	143410.994op/s	0.14%	-1.398	1.973	0.12%	12.337op/s	1	200
trace_buffer/8_senders/no_delay	execution_time	6.304ms	6.619ms ± 0.095ms	6.631ms ± 0.067ms	6.682ms	6.761ms	6.796ms	6.810ms	2.69%	-0.519	0.186	1.43%	0.007ms	1	200
trace_buffer/8_senders/no_delay	throughput	1057282.385op/s	1087953.987op/s ± 15717.907op/s	1085746.746op/s ± 11033.781op/s	1097764.338op/s	1117161.009op/s	1127910.918op/s	1142102.207op/s	5.19%	0.603	0.357	1.44%	1111.424op/s	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
trace_buffer/1_senders/10us_delay	execution_time	[56.699ms; 56.780ms] or [-0.071%; +0.071%]	None	None	None
trace_buffer/1_senders/10us_delay	throughput	[15851.166op/s; 15873.674op/s] or [-0.071%; +0.071%]	None	None	None
trace_buffer/1_senders/1us_delay	execution_time	[50.083ms; 50.091ms] or [-0.008%; +0.008%]	None	None	None
trace_buffer/1_senders/1us_delay	throughput	[17967.380op/s; 17970.202op/s] or [-0.008%; +0.008%]	None	None	None
trace_buffer/1_senders/no_delay	execution_time	[339.897µs; 340.867µs] or [-0.143%; +0.143%]	None	None	None
trace_buffer/1_senders/no_delay	throughput	[2640666.528op/s; 2648053.311op/s] or [-0.140%; +0.140%]	None	None	None
trace_buffer/2_senders/10us_delay	execution_time	[57.096ms; 57.145ms] or [-0.043%; +0.043%]	None	None	None
trace_buffer/2_senders/10us_delay	throughput	[31498.996op/s; 31525.910op/s] or [-0.043%; +0.043%]	None	None	None
trace_buffer/2_senders/1us_delay	execution_time	[50.110ms; 50.119ms] or [-0.009%; +0.009%]	None	None	None
trace_buffer/2_senders/1us_delay	throughput	[35914.781op/s; 35921.039op/s] or [-0.009%; +0.009%]	None	None	None
trace_buffer/2_senders/no_delay	execution_time	[902.137µs; 907.501µs] or [-0.296%; +0.296%]	None	None	None
trace_buffer/2_senders/no_delay	throughput	[1984496.455op/s; 1995956.950op/s] or [-0.288%; +0.288%]	None	None	None
trace_buffer/4_senders/10us_delay	execution_time	[57.468ms; 57.506ms] or [-0.033%; +0.033%]	None	None	None
trace_buffer/4_senders/10us_delay	throughput	[62602.731op/s; 62643.800op/s] or [-0.033%; +0.033%]	None	None	None
trace_buffer/4_senders/1us_delay	execution_time	[50.170ms; 50.180ms] or [-0.010%; +0.010%]	None	None	None
trace_buffer/4_senders/1us_delay	throughput	[71742.123op/s; 71756.687op/s] or [-0.010%; +0.010%]	None	None	None
trace_buffer/4_senders/no_delay	execution_time	[2.500ms; 2.514ms] or [-0.273%; +0.273%]	None	None	None
trace_buffer/4_senders/no_delay	throughput	[1432743.737op/s; 1440667.945op/s] or [-0.276%; +0.276%]	None	None	None
trace_buffer/8_senders/10us_delay	execution_time	[57.930ms; 57.988ms] or [-0.049%; +0.049%]	None	None	None
trace_buffer/8_senders/10us_delay	throughput	[124166.266op/s; 124288.806op/s] or [-0.049%; +0.049%]	None	None	None
trace_buffer/8_senders/1us_delay	execution_time	[50.289ms; 50.306ms] or [-0.017%; +0.017%]	None	None	None
trace_buffer/8_senders/1us_delay	throughput	[143124.850op/s; 143173.212op/s] or [-0.017%; +0.017%]	None	None	None
trace_buffer/8_senders/no_delay	execution_time	[6.606ms; 6.632ms] or [-0.199%; +0.199%]	None	None	None
trace_buffer/8_senders/no_delay	throughput	[1085775.636op/s; 1090132.338op/s] or [-0.200%; +0.200%]	None	None	None

Group 1

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8175M CPU @ 2.50GHz	`aa352ce`	1784304193	dd/no-retry-stats-payload

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
write only interface	execution_time	2.067µs	2.086µs ± 0.009µs	2.085µs ± 0.004µs	2.089µs	2.105µs	2.107µs	2.110µs	1.23%	0.830	0.398	0.42%	0.001µs	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
write only interface	execution_time	[2.085µs; 2.087µs] or [-0.058%; +0.058%]	None	None	None

Group 2

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8175M CPU @ 2.50GHz	`aa352ce`	1784304193	dd/no-retry-stats-payload

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
two way interface	execution_time	21.251µs	21.693µs ± 0.230µs	21.649µs ± 0.126µs	21.801µs	22.145µs	22.324µs	22.490µs	3.89%	0.890	0.756	1.06%	0.016µs	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
two way interface	execution_time	[21.661µs; 21.725µs] or [-0.147%; +0.147%]	None	None	None

Group 3

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8175M CPU @ 2.50GHz	`aa352ce`	1784304193	dd/no-retry-stats-payload

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
concentrator/add_spans_to_concentrator	execution_time	8.425ms	8.454ms ± 0.017ms	8.450ms ± 0.010ms	8.464ms	8.488ms	8.511ms	8.516ms	0.79%	1.167	1.349	0.20%	0.001ms	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
concentrator/add_spans_to_concentrator	execution_time	[8.452ms; 8.457ms] or [-0.028%; +0.028%]	None	None	None

Baseline

Baseline benchmark details

Group 1

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz	`0c6e2a5`	1784223782	main

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
trace_buffer/1_senders/10us_delay	execution_time	56.349ms	56.581ms ± 0.132ms	56.548ms ± 0.072ms	56.645ms	56.832ms	56.982ms	57.107ms	0.99%	1.053	1.514	0.23%	0.009ms	1	200
trace_buffer/1_senders/10us_delay	throughput	15759.794op/s	15906.371op/s ± 37.135op/s	15915.631op/s ± 20.348op/s	15934.488op/s	15954.775op/s	15967.235op/s	15971.768op/s	0.35%	-1.036	1.460	0.23%	2.626op/s	1	200
trace_buffer/1_senders/1us_delay	execution_time	49.980ms	50.075ms ± 0.026ms	50.080ms ± 0.010ms	50.087ms	50.124ms	50.146ms	50.156ms	0.15%	-0.065	1.260	0.05%	0.002ms	1	200
trace_buffer/1_senders/1us_delay	throughput	17944.011op/s	17973.202op/s ± 9.177op/s	17971.190op/s ± 3.731op/s	17977.689op/s	17988.905op/s	17990.209op/s	18007.177op/s	0.20%	0.070	1.259	0.05%	0.649op/s	1	200
trace_buffer/1_senders/no_delay	execution_time	333.391µs	339.933µs ± 3.365µs	339.376µs ± 1.688µs	341.388µs	345.790µs	352.573µs	355.177µs	4.66%	1.572	4.195	0.99%	0.238µs	1	200
trace_buffer/1_senders/no_delay	throughput	2533946.033op/s	2647836.022op/s ± 25825.694op/s	2651922.191op/s ± 13251.352op/s	2663067.486op/s	2680602.991op/s	2687798.439op/s	2699535.265op/s	1.80%	-1.464	3.727	0.97%	1826.152op/s	1	200
trace_buffer/2_senders/10us_delay	execution_time	56.762ms	57.264ms ± 0.204ms	57.245ms ± 0.144ms	57.420ms	57.597ms	57.694ms	57.819ms	1.00%	0.145	-0.451	0.35%	0.014ms	1	200
trace_buffer/2_senders/10us_delay	throughput	31131.672op/s	31433.918op/s ± 111.775op/s	31444.032op/s ± 79.175op/s	31517.498op/s	31602.726op/s	31675.588op/s	31711.348op/s	0.85%	-0.129	-0.456	0.35%	7.904op/s	1	200
trace_buffer/2_senders/1us_delay	execution_time	50.059ms	50.115ms ± 0.039ms	50.106ms ± 0.022ms	50.132ms	50.203ms	50.243ms	50.250ms	0.29%	1.470	2.012	0.08%	0.003ms	1	200
trace_buffer/2_senders/1us_delay	throughput	35821.042op/s	35917.347op/s ± 27.868op/s	35923.635op/s ± 15.965op/s	35938.226op/s	35946.441op/s	35953.211op/s	35957.386op/s	0.09%	-1.466	1.997	0.08%	1.971op/s	1	200
trace_buffer/2_senders/no_delay	execution_time	838.208µs	885.701µs ± 17.906µs	886.240µs ± 11.979µs	895.912µs	916.250µs	929.325µs	938.029µs	5.84%	0.315	0.021	2.02%	1.266µs	1	200
trace_buffer/2_senders/no_delay	throughput	1918917.327op/s	2033111.871op/s ± 40890.300op/s	2031052.072op/s ± 27748.423op/s	2062591.203op/s	2092291.788op/s	2114866.967op/s	2147438.749op/s	5.73%	-0.199	-0.032	2.01%	2891.381op/s	1	200
trace_buffer/4_senders/10us_delay	execution_time	57.164ms	57.474ms ± 0.142ms	57.458ms ± 0.089ms	57.552ms	57.756ms	57.828ms	57.938ms	0.84%	0.573	0.310	0.25%	0.010ms	1	200
trace_buffer/4_senders/10us_delay	throughput	62135.381op/s	62637.552op/s ± 154.221op/s	62654.628op/s ± 97.650op/s	62751.288op/s	62854.817op/s	62960.505op/s	62976.291op/s	0.51%	-0.558	0.289	0.25%	10.905op/s	1	200
trace_buffer/4_senders/1us_delay	execution_time	50.119ms	50.174ms ± 0.037ms	50.166ms ± 0.018ms	50.191ms	50.247ms	50.296ms	50.309ms	0.28%	1.310	1.815	0.07%	0.003ms	1	200
trace_buffer/4_senders/1us_delay	throughput	71558.193op/s	71750.628op/s ± 53.226op/s	71761.810op/s ± 25.974op/s	71784.899op/s	71816.454op/s	71825.687op/s	71829.276op/s	0.09%	-1.305	1.799	0.07%	3.764op/s	1	200
trace_buffer/4_senders/no_delay	execution_time	2.093ms	2.334ms ± 0.087ms	2.329ms ± 0.058ms	2.388ms	2.494ms	2.534ms	2.542ms	9.13%	0.158	-0.183	3.72%	0.006ms	1	200
trace_buffer/4_senders/no_delay	throughput	1416154.020op/s	1544564.786op/s ± 57541.976op/s	1545457.096op/s ± 38152.937op/s	1583477.699op/s	1638050.004op/s	1678964.467op/s	1719768.911op/s	11.28%	0.047	-0.096	3.72%	4068.832op/s	1	200
trace_buffer/8_senders/10us_delay	execution_time	57.656ms	57.904ms ± 0.198ms	57.841ms ± 0.103ms	58.004ms	58.311ms	58.464ms	58.602ms	1.32%	1.104	0.591	0.34%	0.014ms	1	200
trace_buffer/8_senders/10us_delay	throughput	122862.122op/s	124344.169op/s ± 423.354op/s	124479.546op/s ± 220.641op/s	124662.576op/s	124832.901op/s	124875.116op/s	124877.761op/s	0.32%	-1.090	0.548	0.34%	29.936op/s	1	200
trace_buffer/8_senders/1us_delay	execution_time	50.213ms	50.290ms ± 0.053ms	50.276ms ± 0.024ms	50.306ms	50.389ms	50.482ms	50.493ms	0.43%	1.462	2.323	0.10%	0.004ms	1	200
trace_buffer/8_senders/1us_delay	throughput	142594.127op/s	143168.483op/s ± 149.687op/s	143208.216op/s ± 68.232op/s	143273.955op/s	143332.931op/s	143380.910op/s	143388.423op/s	0.13%	-1.455	2.294	0.10%	10.584op/s	1	200
trace_buffer/8_senders/no_delay	execution_time	5.481ms	6.616ms ± 0.155ms	6.646ms ± 0.077ms	6.718ms	6.767ms	6.789ms	6.812ms	2.50%	-3.097	16.523	2.33%	0.011ms	1	200
trace_buffer/8_senders/no_delay	throughput	1056883.682op/s	1088959.952op/s ± 27710.537op/s	1083311.376op/s ± 12409.484op/s	1096462.232op/s	1132034.650op/s	1169288.494op/s	1313660.457op/s	21.26%	3.835	24.112	2.54%	1959.431op/s	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
trace_buffer/1_senders/10us_delay	execution_time	[56.563ms; 56.600ms] or [-0.032%; +0.032%]	None	None	None
trace_buffer/1_senders/10us_delay	throughput	[15901.224op/s; 15911.517op/s] or [-0.032%; +0.032%]	None	None	None
trace_buffer/1_senders/1us_delay	execution_time	[50.071ms; 50.078ms] or [-0.007%; +0.007%]	None	None	None
trace_buffer/1_senders/1us_delay	throughput	[17971.930op/s; 17974.473op/s] or [-0.007%; +0.007%]	None	None	None
trace_buffer/1_senders/no_delay	execution_time	[339.466µs; 340.399µs] or [-0.137%; +0.137%]	None	None	None
trace_buffer/1_senders/no_delay	throughput	[2644256.830op/s; 2651415.215op/s] or [-0.135%; +0.135%]	None	None	None
trace_buffer/2_senders/10us_delay	execution_time	[57.235ms; 57.292ms] or [-0.049%; +0.049%]	None	None	None
trace_buffer/2_senders/10us_delay	throughput	[31418.427op/s; 31449.409op/s] or [-0.049%; +0.049%]	None	None	None
trace_buffer/2_senders/1us_delay	execution_time	[50.110ms; 50.120ms] or [-0.011%; +0.011%]	None	None	None
trace_buffer/2_senders/1us_delay	throughput	[35913.485op/s; 35921.209op/s] or [-0.011%; +0.011%]	None	None	None
trace_buffer/2_senders/no_delay	execution_time	[883.219µs; 888.182µs] or [-0.280%; +0.280%]	None	None	None
trace_buffer/2_senders/no_delay	throughput	[2027444.869op/s; 2038778.873op/s] or [-0.279%; +0.279%]	None	None	None
trace_buffer/4_senders/10us_delay	execution_time	[57.454ms; 57.493ms] or [-0.034%; +0.034%]	None	None	None
trace_buffer/4_senders/10us_delay	throughput	[62616.179op/s; 62658.926op/s] or [-0.034%; +0.034%]	None	None	None
trace_buffer/4_senders/1us_delay	execution_time	[50.169ms; 50.179ms] or [-0.010%; +0.010%]	None	None	None
trace_buffer/4_senders/1us_delay	throughput	[71743.251op/s; 71758.004op/s] or [-0.010%; +0.010%]	None	None	None
trace_buffer/4_senders/no_delay	execution_time	[2.322ms; 2.346ms] or [-0.517%; +0.517%]	None	None	None
trace_buffer/4_senders/no_delay	throughput	[1536590.021op/s; 1552539.550op/s] or [-0.516%; +0.516%]	None	None	None
trace_buffer/8_senders/10us_delay	execution_time	[57.877ms; 57.932ms] or [-0.047%; +0.047%]	None	None	None
trace_buffer/8_senders/10us_delay	throughput	[124285.496op/s; 124402.841op/s] or [-0.047%; +0.047%]	None	None	None
trace_buffer/8_senders/1us_delay	execution_time	[50.283ms; 50.298ms] or [-0.015%; +0.015%]	None	None	None
trace_buffer/8_senders/1us_delay	throughput	[143147.738op/s; 143189.229op/s] or [-0.014%; +0.014%]	None	None	None
trace_buffer/8_senders/no_delay	execution_time	[6.594ms; 6.637ms] or [-0.324%; +0.324%]	None	None	None
trace_buffer/8_senders/no_delay	throughput	[1085119.538op/s; 1092800.366op/s] or [-0.353%; +0.353%]	None	None	None

Group 1

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8175M CPU @ 2.50GHz	`0c6e2a5`	1784223782	main

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
write only interface	execution_time	2.071µs	2.088µs ± 0.009µs	2.086µs ± 0.003µs	2.090µs	2.109µs	2.113µs	2.130µs	2.08%	1.633	3.443	0.41%	0.001µs	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
write only interface	execution_time	[2.087µs; 2.089µs] or [-0.057%; +0.057%]	None	None	None

Group 2

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8175M CPU @ 2.50GHz	`0c6e2a5`	1784223782	main

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
two way interface	execution_time	20.838µs	21.679µs ± 1.341µs	21.562µs ± 0.129µs	21.698µs	22.001µs	22.553µs	40.233µs	86.59%	13.341	181.992	6.17%	0.095µs	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
two way interface	execution_time	[21.493µs; 21.865µs] or [-0.857%; +0.857%]	None	None	None

Group 3

cpu_model	git_commit_sha	git_commit_date	git_branch
Intel(R) Xeon(R) Platinum 8175M CPU @ 2.50GHz	`0c6e2a5`	1784223782	main

scenario	metric	min	mean ± sd	median ± mad	p75	p95	p99	max	peak_to_median_ratio	skewness	kurtosis	cv	sem	runs	sample_size
concentrator/add_spans_to_concentrator	execution_time	8.416ms	8.444ms ± 0.019ms	8.438ms ± 0.011ms	8.454ms	8.485ms	8.496ms	8.501ms	0.74%	0.952	0.071	0.23%	0.001ms	1	200

scenario	metric	95% CI mean	Shapiro-Wilk pvalue	Ljung-Box pvalue (lag=1)	Dip test pvalue
concentrator/add_spans_to_concentrator	execution_time	[8.441ms; 8.447ms] or [-0.032%; +0.032%]	None	None	None

dd-octo-sts · 2026-07-17T16:41:05Z

Artifact Size Benchmark Report

aarch64-alpine-linux-musl

Artifact	Baseline	Commit	Change
/aarch64-alpine-linux-musl/lib/libdatadog_profiling.so	7.88 MB	7.88 MB	0% (0 B) 👌
/aarch64-alpine-linux-musl/lib/libdatadog_profiling.a	86.33 MB	86.33 MB	+0% (+56 B) 👌

aarch64-unknown-linux-gnu

Artifact	Baseline	Commit	Change
/aarch64-unknown-linux-gnu/lib/libdatadog_profiling.so	10.62 MB	10.62 MB	0% (0 B) 👌
/aarch64-unknown-linux-gnu/lib/libdatadog_profiling.a	97.54 MB	97.54 MB	+0% (+80 B) 👌

libdatadog-x64-windows

Artifact	Baseline	Commit	Change
/libdatadog-x64-windows/debug/dynamic/datadog_profiling_ffi.dll	25.58 MB	25.58 MB	0% (0 B) 👌
/libdatadog-x64-windows/debug/dynamic/datadog_profiling_ffi.lib	89.18 KB	89.18 KB	0% (0 B) 👌
/libdatadog-x64-windows/debug/dynamic/datadog_profiling_ffi.pdb	185.53 MB	185.53 MB	0% (0 B) 👌
/libdatadog-x64-windows/debug/static/datadog_profiling_ffi.lib	958.60 MB	958.60 MB	0% (0 B) 👌
/libdatadog-x64-windows/release/dynamic/datadog_profiling_ffi.dll	8.37 MB	8.37 MB	0% (0 B) 👌
/libdatadog-x64-windows/release/dynamic/datadog_profiling_ffi.lib	89.18 KB	89.18 KB	0% (0 B) 👌
/libdatadog-x64-windows/release/dynamic/datadog_profiling_ffi.pdb	24.76 MB	24.76 MB	0% (0 B) 👌
/libdatadog-x64-windows/release/static/datadog_profiling_ffi.lib	49.28 MB	49.28 MB	-0% (-8 B) 👌

libdatadog-x86-windows

Artifact	Baseline	Commit	Change
/libdatadog-x86-windows/debug/dynamic/datadog_profiling_ffi.dll	22.23 MB	22.23 MB	+0% (+512 B) 👌
/libdatadog-x86-windows/debug/dynamic/datadog_profiling_ffi.lib	90.58 KB	90.58 KB	0% (0 B) 👌
/libdatadog-x86-windows/debug/dynamic/datadog_profiling_ffi.pdb	189.98 MB	190.01 MB	+.01% (+24.00 KB) 🔍
/libdatadog-x86-windows/debug/static/datadog_profiling_ffi.lib	946.54 MB	946.54 MB	+0% (+80 B) 👌
/libdatadog-x86-windows/release/dynamic/datadog_profiling_ffi.dll	6.47 MB	6.47 MB	0% (0 B) 👌
/libdatadog-x86-windows/release/dynamic/datadog_profiling_ffi.lib	90.58 KB	90.58 KB	0% (0 B) 👌
/libdatadog-x86-windows/release/dynamic/datadog_profiling_ffi.pdb	26.58 MB	26.58 MB	0% (0 B) 👌
/libdatadog-x86-windows/release/static/datadog_profiling_ffi.lib	46.89 MB	46.89 MB	-0% (-8 B) 👌

x86_64-alpine-linux-musl

Artifact	Baseline	Commit	Change
/x86_64-alpine-linux-musl/lib/libdatadog_profiling.a	77.08 MB	77.08 MB	-0% (-8 B) 👌
/x86_64-alpine-linux-musl/lib/libdatadog_profiling.so	8.83 MB	8.83 MB	0% (0 B) 👌

x86_64-unknown-linux-gnu

Artifact	Baseline	Commit	Change
/x86_64-unknown-linux-gnu/lib/libdatadog_profiling.a	92.50 MB	92.50 MB	0% (0 B) 👌
/x86_64-unknown-linux-gnu/lib/libdatadog_profiling.so	10.74 MB	10.74 MB	0% (0 B) 👌

fix(trace-stats): disable retries for stats payload

8e12034

datadog-datadog-prod-us1 Bot added the Bits AI label Jul 17, 2026

VianneyRuhlmann marked this pull request as ready for review July 17, 2026 15:58

VianneyRuhlmann requested a review from a team as a code owner July 17, 2026 15:58

chatgpt-codex-connector Bot reviewed Jul 17, 2026

View reviewed changes

Comment thread libdd-trace-stats/src/stats_exporter.rs

test(trace-stats): expect single attempt in fail test

aa352ce

VianneyRuhlmann changed the title ~~fix(stats): disable retries for stats payload sends~~ Disable retries for stats payload sends Jul 17, 2026

Uh oh!

Conversation

VianneyRuhlmann commented Jul 17, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

What does this PR do?

Motivation

Changes

How to test the change?

Uh oh!

datadog-prod-us1-6 Bot commented Jul 17, 2026 • edited by datadog-prod-us1-3 Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

datadog-datadog-prod-us1-2 Bot commented Jul 17, 2026

Uh oh!

github-actions Bot commented Jul 17, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

📚 Documentation Check Results

📦 libdd-trace-stats - 872 warning(s)

Uh oh!

github-actions Bot commented Jul 17, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🔒 Cargo Deny Results

📦 libdd-trace-stats - 2 error(s)

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

Uh oh!

datadog-prod-us1-6 Bot commented Jul 17, 2026 • edited by datadog-datadog-us1-prod Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

⚠️ Warnings

ℹ️ Info

Uh oh!

pr-commenter Bot commented Jul 17, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Benchmarks

Comparison

Explanation

More details about the CI and significant changes

scenario:trace_buffer/4_senders/no_delay

Explanation

More details about the CI and significant changes

Candidate

Group 1

Group 1

Group 2

Group 3

Baseline

Group 1

Group 1

Group 2

Group 3

Uh oh!

dd-octo-sts Bot commented Jul 17, 2026

Artifact Size Benchmark Report

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

VianneyRuhlmann commented Jul 17, 2026 •

edited

Loading

datadog-prod-us1-6 Bot commented Jul 17, 2026 •

edited by datadog-prod-us1-3 Bot

Loading

github-actions Bot commented Jul 17, 2026 •

edited

Loading

📦 `libdd-trace-stats` - 872 warning(s)

github-actions Bot commented Jul 17, 2026 •

edited

Loading

📦 `libdd-trace-stats` - 2 error(s)

datadog-prod-us1-6 Bot commented Jul 17, 2026 •

edited by datadog-datadog-us1-prod Bot

Loading

pr-commenter Bot commented Jul 17, 2026 •

edited

Loading